36 citations · 36 across the 1 of their papers we have counts for
2 papers
cs.DC2024
DistServe: Disaggregating Prefill and Decoding for Goodput-optimized Large Language Model Serving
Yinmin Zhong, Shengyu Liu, Junda Chen +5
DistServe improves the performance of large language models (LLMs) serving by disaggregating the prefill and decoding computation. Existing LLM serving systems colocate the two pha…
cs.DC2023★ 36 cited
Oobleck: Resilient Distributed Training of Large Models Using Pipeline Templates
Insu Jang, Zhenning Yang, Zhen Zhang +2
Oobleck enables resilient distributed training of large DNN models with guaranteed fault tolerance. It takes a planning-execution co-design approach, where it first generates a set…